Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3754 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.4297. Min Act: -0.0000

Data Index: 698439 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.3848. Min Act: -0.0000

Data Index: 19974 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.3448. Min Act: -0.0000

Data Index: 614092 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.3675. Min Act: -0.0000

Data Index: 655261 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.3684. Min Act: -0.0000

Data Index: 485926 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.3434. Min Act: -0.0000

Data Index: 685000 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.3542. Min Act: -0.0000

Data Index: 872086 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.3360. Min Act: -0.0000

Data Index: 1134774 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1320170 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.3110. Min Act: -0.0000

Data Index: 161053 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.3145. Min Act: -0.0000

Data Index: 783605 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.2896. Min Act: -0.0000

Data Index: 895539 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.3054. Min Act: -0.0000

Data Index: 954838 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.3011. Min Act: -0.0000

Data Index: 138340 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.2965. Min Act: -0.0000

Data Index: 174880 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.2824. Min Act: -0.0000

Data Index: 1196354 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.2904. Min Act: -0.0000

Data Index: 28627 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.2771. Min Act: -0.0000

Data Index: 577133 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.2730. Min Act: -0.0000

Data Index: 354521 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.2913. Min Act: -0.0000

Data Index: 1327661 (C4 (Web Text))

Max Activating Token Index: 970